{"id":2567091,"url":"https://alion.io/job/tensordyne-working-student-llm-quantization-inference-performance","title":"Working Student - LLM Quantization & Inference Performance","company":{"id":39776,"name":"Tensordyne","domain":"tensordyne.ai","url":"https://alion.io/company/tensordyne","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":{"grade":"A","score":90,"open_postings":23,"ghost_share":0,"stale_share":0.217,"repost_share":0,"time_to_fill_p50_days":214,"computed_at":"2026-11-03T05:54:40Z"}},"role":"Early Careers","role_family":"Early Careers","seniority":"intern","employment_type":"part_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Munich, Germany"],"countries":["DE"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":37000,"max_usd":65000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":55},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false},{"name":"Multimodal AI","optional":false},{"name":"Post-training","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Quantization","optional":false},{"name":"Qwen","optional":false}],"status":"live","first_seen_at":"2026-10-14T20:38:11Z","employer_posted_date":"2026-10-26","last_verified_at":"2026-11-03T17:57:10Z","board_verified":true,"closed_at":null,"days_open":19,"trust":{"level":"ok","repost_count":1,"flags":[],"days_open":19},"description":"About Tensordyne (formerly Recogni)\nAI is transforming our world. It can perform cognitive functions that previously only humans could do, such as perceiving interactions across different modalities and environments - with the ability to quickly learn and then solve complex problems. Tensordyne is an AI system solution company that builds very high-performance, low-power generative AI inference systems. Our mission, through the creation of custom silicon, hardware and software, is to enable multimodal Generative AI inference acceleration at scale, with safe, sustainable, high-performance systems for our hyperscaler and neocloud data center customers. We are at the leading edge of advancing the latest research and product improvements for generative Al inference solutions that will make Al even more advantageous for compelling new generative AI applications.Tensordyne is a well funded, fast-paced startup company with headquarters in both Sunnyvale, CA, and Munich, Germany. We also have many talented team members working remotely across North America and Europe. We take care of our people and their families with comprehensive benefits, competitive compensation, flexible spending options, and recognition programs, because building category-defining technology starts with a healthy, supported team. Come join us as we shape the future of multimodal generative artificial intelligence!\nRole summary\nHow much numerical precision does an LLM need, and where in the model architecture does it matter most? When does quantization improve runtime, and what does it cost in model quality?\nWe’re looking for a motivated working student to help turn these questions into experiments and experiments into maintainable code. You’ll explore optimization methods and build reusable evaluation tooling. You’ll work closely with our quantization, compiler, and runtime engineers, and your findings will directly influence how we optimize models for Tensordyne hardware.\nWhat you will do\nModel quality evaluation: Measure how low-precision computation affects performance on coding and reasoning benchmarks. Diagnose where quantization has the greatest impact.\nQuantization research: Implement and compare post-training quantization methods to improve inference efficiency while preserving task accuracy.\nBuild reproducible tooling: Automate evaluations, track configurations and results, and make experiments accessible to engineers and AI agents.\nMeasure runtime performance: Characterize latency, throughput, and memory usage to understand bottlenecks under different deployment scenarios.\nA first project could involve exploring the quality-performance Pareto frontier of a Qwen or LlaMa model. You’ll experiment with 16-bit, 8-bit, and 4-bit quantization configurations to find the best runtime-quality tradeoff.\nCore qualifications\nCurrent enrollment in Computer Science, Mathematics, Electrical Engineering, Machine Learning, or a related master’s degree program.\nStrong Python and PyTorch skills, including the ability to understand and modify model implementations.\nEffective use of AI coding tools and critical review of their output.\nAn experimental mindset: you can formulate hypotheses, design comparisons, and draw careful conclusions from noisy results.\nClear communication and the ability to present experimental findings and technical tradeoffs to the team.\nStrong pluses: experience with quantization, LLM evaluation, performance profiling, or inference optimization.\nThis role is for you if you thrive on responsibility, learn quickly, and are naturally proactive.\nWhat we offer\nJoin a deep-tech team building the next generation of AI inference systems. Put your university knowledge into practice with leading open-source LLMs, deepen your understanding of quantization and inference optimization, and build skills in experimental design, software engineering, and AI coding tools. You’ll own a focused project, receive close mentorship from experienced engineers, and have room to explore ideas that shape our optimization methods.\nTensordyne's culture was built on the following values\nPut people first. We only succeed when our people succeed.\nEthics and integrity always. Be open, honest, and respectful of everyone.\nThink Big. Be ambitious and have audacious goals.\nAim for excellence. Quality and excellence count in everything we do.\nOwn it and get it done. Results matter!\nMake each person better together than they would be as an individual.\nEmbrace each other’s differences, and embrace that there will be differences.\nTensordyne is an equal opportunity employer. We believe diverse teams are better equipped to solve complex problems and build exceptional technology. All qualified applicants will receive consideration for employment without regard to age, color, gender identity or expression, marital status, national origin, disability, protected veteran status, race, religion, pregnancy, sexual orientation, or any other characteristic protected by applicable laws, regulations, and ordinances.\nA note to recruitment agencies: Please do not contact Tensordyne employees or leaders regarding this role. We do not accept unsolicited agency resumes and are not responsible for fees associated with unsolicited submissions.","description_format":"text","description_chars":5258,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"United States","iso":"US","kind":"region"},{"name":"Canada","iso":"CA","kind":"region"},{"name":"Mexico","iso":"MX","kind":"region"},{"name":"Anguilla","iso":"AI","kind":"region"},{"name":"Antigua and Barbuda","iso":"AG","kind":"region"},{"name":"Aruba","iso":"AW","kind":"region"},{"name":"Bahamas","iso":"BS","kind":"region"},{"name":"Barbados","iso":"BB","kind":"region"},{"name":"Belize","iso":"BZ","kind":"region"},{"name":"Bermuda","iso":"BM","kind":"region"},{"name":"British Virgin Islands","iso":"VG","kind":"region"},{"name":"Bonaire, Sint Eustatius and Saba","iso":"BQ","kind":"region"},{"name":"Cayman Islands","iso":"KY","kind":"region"},{"name":"Costa Rica","iso":"CR","kind":"region"},{"name":"Curaçao","iso":"CW","kind":"region"},{"name":"Dominica","iso":"DM","kind":"region"},{"name":"Dominican Republic","iso":"DO","kind":"region"},{"name":"El Salvador","iso":"SV","kind":"region"},{"name":"Greenland","iso":"GL","kind":"region"},{"name":"Grenada","iso":"GD","kind":"region"},{"name":"Guadeloupe","iso":"GP","kind":"region"},{"name":"Guatemala","iso":"GT","kind":"region"},{"name":"Haiti","iso":"HT","kind":"region"},{"name":"Honduras","iso":"HN","kind":"region"},{"name":"Jamaica","iso":"JM","kind":"region"},{"name":"Martinique","iso":"MQ","kind":"region"},{"name":"Montserrat","iso":"MS","kind":"region"},{"name":"Nicaragua","iso":"NI","kind":"region"},{"name":"Panama","iso":"PA","kind":"region"},{"name":"Puerto Rico","iso":"PR","kind":"region"},{"name":"Saint Kitts and Nevis","iso":"KN","kind":"region"},{"name":"Saint Lucia","iso":"LC","kind":"region"},{"name":"Saint Vincent and the Grenadines","iso":"VC","kind":"region"},{"name":"Saint-Pierre and Miquelon","iso":"PM","kind":"region"},{"name":"Sint Maarten","iso":"SX","kind":"region"},{"name":"Trinidad and Tobago","iso":"TT","kind":"region"},{"name":"Turks and Caicos Islands","iso":"TC","kind":"region"},{"name":"United States Virgin Islands","iso":"VI","kind":"region"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Processors, MCUs & AI Chips","AI Compute & Inference","AI Chips & Accelerators"],"lifecycle":[{"event":"open","at":"2026-10-14T22:08:54Z"},{"event":"close","at":"2026-10-15T13:16:25Z"},{"event":"reopen","at":"2026-10-26T12:42:27Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":19,"expected_fill_days":214,"reasons":["conf:2","velocity","win:early","comp:junior"],"computed_at":"2026-11-03T05:54:40Z"},"pay":null,"html_url":"https://alion.io/job/tensordyne-working-student-llm-quantization-inference-performance","json_url":"https://alion.io/job/tensordyne-working-student-llm-quantization-inference-performance.json","meta":{"generated_at":"2026-11-03T19:09:24Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":1133,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-04T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":39776},"rest":"https://alion.io/mcp/rest/get_company?id=39776"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Ftensordyne-working-student-llm-quantization-inference-performance"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Ftensordyne-working-student-llm-quantization-inference-performance"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Ftensordyne-working-student-llm-quantization-inference-performance"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/tensordyne-working-student-llm-quantization-inference-performance\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftensordyne-working-student-llm-quantization-inference-performance"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":2567091}},{"tool":"search_jobs","arguments":{"company":"tensordyne.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":2567091},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}